Files
sam-kd/ai_sam/ref/utils/audio.ts
hskwon aca1767eb9 초기 커밋: 5130 레거시 시스템
- URL 하드코딩 → .env APP_URL 기반 동적 URL로 변경
- DB 연결 하드코딩 → .env 기반으로 변경
- MySQL strict mode DATE 오류 수정
2025-12-10 20:14:31 +09:00

58 lines
1.7 KiB
TypeScript

import { Blob } from '@google/genai';
// Convert base64 string to raw bytes
export function decode(base64: string): Uint8Array {
const binaryString = atob(base64);
const len = binaryString.length;
const bytes = new Uint8Array(len);
for (let i = 0; i < len; i++) {
bytes[i] = binaryString.charCodeAt(i);
}
return bytes;
}
// Convert raw bytes to base64 string
export function encode(bytes: Uint8Array): string {
let binary = '';
const len = bytes.byteLength;
for (let i = 0; i < len; i++) {
binary += String.fromCharCode(bytes[i]);
}
return btoa(binary);
}
// Decode raw PCM bytes into an AudioBuffer
export async function decodeAudioData(
data: Uint8Array,
ctx: AudioContext,
sampleRate: number = 24000,
numChannels: number = 1
): Promise<AudioBuffer> {
const dataInt16 = new Int16Array(data.buffer);
const frameCount = dataInt16.length / numChannels;
const buffer = ctx.createBuffer(numChannels, frameCount, sampleRate);
for (let channel = 0; channel < numChannels; channel++) {
const channelData = buffer.getChannelData(channel);
for (let i = 0; i < frameCount; i++) {
channelData[i] = dataInt16[i * numChannels + channel] / 32768.0;
}
}
return buffer;
}
// Create a Blob formatted for the Gemini Live API (PCM 16kHz)
export function createPcmBlob(data: Float32Array): Blob {
const l = data.length;
const int16 = new Int16Array(l);
for (let i = 0; i < l; i++) {
// Clamp values to [-1, 1] to prevent distortion
const s = Math.max(-1, Math.min(1, data[i]));
int16[i] = s < 0 ? s * 0x8000 : s * 0x7FFF;
}
return {
data: encode(new Uint8Array(int16.buffer)),
mimeType: 'audio/pcm;rate=16000',
};
}